mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Zhang Qiao <zhangqiao22@huawei.com>
To: Jens Axboe <axboe@kernel.dk>, <linux-kernel@vger.kernel.org>
Cc: <peterz@infradead.org>, <tglx@linutronix.de>
Subject: Re: [PATCH 2/4] sched/core: change rq->nr_iowait type to atomic_long_t
Date: Tue, 20 Aug 2024 10:14:24 +0800	[thread overview]
Message-ID: <b8fc12fa-57c8-4578-883a-a452f4ff1127@huawei.com> (raw)
In-Reply-To: <20240819154259.215504-3-axboe@kernel.dk>



在 2024/8/19 23:39, Jens Axboe 写道:
> In preparation for storing two separate iowait states in there, bump the
> size from a 32-bit to a 64-bit size, for 64-bit kernels. On 32-bit
> archs, the type remains a 32-bit size.
> 
> Note that on 32-bit, the number of tasks are limited to 0x8000, which
> fits just fine in even half of the existing 32-bit atomic_t. For 64-bit,
> no such limit exists, hence play it safe and make it a 64-bit atomic.
> 
> Signed-off-by: Jens Axboe <axboe@kernel.dk>

Reviewed-by: Zhang Qiao <zhangqiao22@huawei.com>

> ---
>  kernel/sched/core.c  | 8 ++++----
>  kernel/sched/sched.h | 2 +-
>  2 files changed, 5 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 9bf1b67818d0..7e04b84dcc55 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3543,17 +3543,17 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
>  
>  static void task_iowait_inc(struct task_struct *p)
>  {
> -	atomic_inc(&task_rq(p)->nr_iowait);
> +	atomic_long_inc(&task_rq(p)->nr_iowait);
>  }
>  
>  static void task_iowait_dec(struct task_struct *p)
>  {
> -	atomic_dec(&task_rq(p)->nr_iowait);
> +	atomic_long_dec(&task_rq(p)->nr_iowait);
>  }
>  
>  int rq_iowait(struct rq *rq)
>  {
> -	return atomic_read(&rq->nr_iowait);
> +	return atomic_long_read(&rq->nr_iowait);
>  }
>  
>  static void
> @@ -8372,7 +8372,7 @@ void __init sched_init(void)
>  #endif
>  #endif /* CONFIG_SMP */
>  		hrtick_rq_init(rq);
> -		atomic_set(&rq->nr_iowait, 0);
> +		atomic_long_set(&rq->nr_iowait, 0);
>  		fair_server_init(rq);
>  
>  #ifdef CONFIG_SCHED_CORE
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index b6b3b565bcb1..da2e67621f39 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -1082,7 +1082,7 @@ struct rq {
>  	u64			clock_idle_copy;
>  #endif
>  
> -	atomic_t		nr_iowait;
> +	atomic_long_t		nr_iowait;>
>  #ifdef CONFIG_SCHED_DEBUG
>  	u64 last_seen_need_resched_ns;

  reply	other threads:[~2024-08-20  2:14 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-08-19 15:39 [PATCHSET v6 0/4] Split iowait into two states Jens Axboe
2024-08-19 15:39 ` [PATCH 1/4] sched/core: add helpers for iowait handling Jens Axboe
2024-08-19 15:39 ` [PATCH 2/4] sched/core: change rq->nr_iowait type to atomic_long_t Jens Axboe
2024-08-20  2:14   ` Zhang Qiao [this message]
2024-08-19 15:39 ` [PATCH 3/4] sched/core: have io_schedule_prepare() return a long Jens Axboe
2024-09-05  9:57   ` Peter Zijlstra
2024-08-19 15:39 ` [PATCH 4/4] sched/core: split iowait state into two states Jens Axboe
2024-09-05 10:55   ` Peter Zijlstra
2024-08-21 14:54 ` [PATCHSET v6 0/4] Split iowait " Christian Loehle
2024-08-21 15:04   ` Jens Axboe
2024-08-21 15:57     ` Christian Loehle
2024-08-24 15:34       ` Jens Axboe
2024-09-04 14:28 ` Peter Zijlstra
2024-09-04 14:41   ` Jens Axboe
2024-09-04 14:49     ` Jens Axboe
2024-09-05  9:51     ` Peter Zijlstra
2024-09-04 14:42   ` Rafael J. Wysocki
2024-09-04 15:18     ` Rafael J. Wysocki
2024-09-05  9:29       ` Christian Loehle
2024-09-05 10:40         ` Rafael J. Wysocki
2024-09-05  9:36       ` Peter Zijlstra
2024-09-05 10:31         ` Christian Loehle
2024-09-05 11:00           ` Peter Zijlstra
2024-09-05 11:09             ` Christian Loehle
2025-03-31  9:02 ` Pavel Begunkov
2025-03-31 10:33   ` Christian Loehle
2025-04-01  8:21     ` Pavel Begunkov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=b8fc12fa-57c8-4578-883a-a452f4ff1127@huawei.com \
    --to=zhangqiao22@huawei.com \
    --cc=axboe@kernel.dk \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®